AppAgent: Multimodal Agents as Smartphone Users, an LLM-based multimodal agent framework designed to operate smartphone apps.

🧠「大模型」2小时完全从0训练64M的小参数LLM！Train a 64M-parameter LLM from scratch in just 2h!

Runnable ClaudeCode source code

"OpenHarness: Open Agent Harness"

🇨🇳 OpenClaw（AI 智能体）新手入门+中文最佳用例大全 | 37 个真实场景（国内+国际）：自动化办公、内容创作、服务器运维、个人助理、知识管理 | 零基础新手友好 | Chinese guide for OpenClaw AI agent use cases

The open source coding agent.

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

An AI SKILL that provide design intelligence for building professional UI/UX multiple platforms

Speech-to-text, text-to-speech, speaker diarization, speech enhancement, source separation, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Andr…

Claude Code 逆向工程研究仓库

Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.

Open-source live-chat, email support, omni-channel desk. An alternative to Intercom, Zendesk, Salesforce Service Cloud etc. 🔥💬

A high-throughput and memory-efficient inference and serving engine for LLMs (Windows build & kernels)

FULL Augment Code, Claude Code, Cluely, CodeBuddy, Comet, Cursor, Devin AI, Junie, Kiro, Leap.new, Lovable, Manus Agent Tools, NotionAI, Orchids.app, Perplexity, Poke, Qoder, Replit, Same.dev, Trae…

[ICLR2025 Spotlight] SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models

Fork of the Triton language and compiler for Windows support and easy installation

基于大模型搭建的聊天机器人，同时支持 微信公众号、企业微信应用、飞书、钉钉 等接入，可选择ChatGPT/Claude/DeepSeek/文心一言/讯飞星火/通义千问/ Gemini/GLM-4/Kimi/LinkAI，能处理文本、语音和图片，访问操作系统和互联网，支持基于自有知识库进行定制企业智能客服。

开源的端到端产品级通用智能体

A Multi-Agent platform that enables AI agents to collaborate effectively, helping you build powerful agent teams for solving complex tasks.

A backend management system based on vue3, typescript, element-plus, and vite

dnalogel 是如视三维空间交互增强插件库，为三维空间提供强有力辅助，增强空间数字表达能力，强化空间视觉体验效果。打破三维空间壁垒，创造数字空间的无限可能。

Qwen2.5-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

Run your own AI cluster at home with everyday devices 📱💻 🖥️⌚

Vreo (VR Video 缩写) 是基于如视三维渲染引擎 Five 和 用户界面构建库 React 实现的如视 3D 空间剧本播放器。

Let your Claude able to think

如视开发者文档

No fortress, purely open ground. OpenManus is Coming.

Open source codebase powering the HuggingChat app

DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding